Mirror Gradient: Towards Robust Multimodal Recommender Systems via
Exploring Flat Local Minima
- URL: http://arxiv.org/abs/2402.11262v1
- Date: Sat, 17 Feb 2024 12:27:30 GMT
- Title: Mirror Gradient: Towards Robust Multimodal Recommender Systems via
Exploring Flat Local Minima
- Authors: Shanshan Zhong, Zhongzhan Huang, Daifeng Li, Wushao Wen, Jinghui Qin,
Liang Lin
- Abstract summary: We analyze multimodal recommender systems from the novel perspective of flat local minima.
We propose a concise yet effective gradient strategy called Mirror Gradient (MG)
We find that the proposed MG can complement existing robust training methods and be easily extended to diverse advanced recommendation models.
- Score: 54.06000767038741
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multimodal recommender systems utilize various types of information to model
user preferences and item features, helping users discover items aligned with
their interests. The integration of multimodal information mitigates the
inherent challenges in recommender systems, e.g., the data sparsity problem and
cold-start issues. However, it simultaneously magnifies certain risks from
multimodal information inputs, such as information adjustment risk and inherent
noise risk. These risks pose crucial challenges to the robustness of
recommendation models. In this paper, we analyze multimodal recommender systems
from the novel perspective of flat local minima and propose a concise yet
effective gradient strategy called Mirror Gradient (MG). This strategy can
implicitly enhance the model's robustness during the optimization process,
mitigating instability risks arising from multimodal information inputs. We
also provide strong theoretical evidence and conduct extensive empirical
experiments to show the superiority of MG across various multimodal
recommendation models and benchmarks. Furthermore, we find that the proposed MG
can complement existing robust training methods and be easily extended to
diverse advanced recommendation models, making it a promising new and
fundamental paradigm for training multimodal recommender systems. The code is
released at https://github.com/Qrange-group/Mirror-Gradient.
Related papers
- LANE: Logic Alignment of Non-tuning Large Language Models and Online Recommendation Systems for Explainable Reason Generation [15.972926854420619]
Leveraging large language models (LLMs) offers new opportunities for comprehensive recommendation logic generation.
Fine-tuning LLM models for recommendation tasks incurs high computational costs and alignment issues with existing systems.
In this work, our proposed effective strategy LANE aligns LLMs with online recommendation systems without additional LLMs tuning.
arXiv Detail & Related papers (2024-07-03T06:20:31Z) - MinT: Boosting Generalization in Mathematical Reasoning via Multi-View
Fine-Tuning [53.90744622542961]
Reasoning in mathematical domains remains a significant challenge for small language models (LMs)
We introduce a new method that exploits existing mathematical problem datasets with diverse annotation styles.
Experimental results show that our strategy enables a LLaMA-7B model to outperform prior approaches.
arXiv Detail & Related papers (2023-07-16T05:41:53Z) - Mining Stable Preferences: Adaptive Modality Decorrelation for
Multimedia Recommendation [23.667430143035787]
We propose a novel MOdality DEcorrelating STable learning framework, MODEST for brevity, to learn users' stable preference.
Inspired by sample re-weighting techniques, the proposed method aims to estimate a weight for each item, such that the features from different modalities in the weighted distribution are decorrelated.
Our method could be served as a play-and-plug module for existing multimedia recommendation backbones.
arXiv Detail & Related papers (2023-06-25T09:09:11Z) - A Survey on Large Language Models for Recommendation [77.91673633328148]
Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP)
This survey presents a taxonomy that categorizes these models into two major paradigms, respectively Discriminative LLM for Recommendation (DLLM4Rec) and Generative LLM for Recommendation (GLLM4Rec)
arXiv Detail & Related papers (2023-05-31T13:51:26Z) - RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems [100.54655931138444]
We propose a more holistic view of robustness for recommender systems that encompasses multiple dimensions.
We present a robustness evaluation toolkit, Robustness Gym for RecSys, that allows us to quickly and uniformly evaluate the robustness of recommender system models.
arXiv Detail & Related papers (2022-01-12T10:32:53Z) - MultiHead MultiModal Deep Interest Recommendation Network [0.0]
This paper adds multi-head and multi-modal modules to the DINciteAuthors01 model.
Experiments show that the multi-head multi-modal DIN improves the recommendation prediction effect, and outperforms current state-of-the-art methods on various comprehensive indicators.
arXiv Detail & Related papers (2021-10-19T18:59:02Z) - Sample-Rank: Weak Multi-Objective Recommendations Using Rejection
Sampling [0.5156484100374059]
We introduce a method involving multi-goal sampling followed by ranking for user-relevance (Sample-Rank) to nudge recommendations towards multi-objective goals of the marketplace.
The proposed method's novelty is that it reduces the MO recommendation problem to sampling from a desired multi-goal distribution then using it to build a production-friendly learning-to-rank model.
arXiv Detail & Related papers (2020-08-24T09:17:18Z) - Self-Supervised Reinforcement Learning for Recommender Systems [77.38665506495553]
We propose self-supervised reinforcement learning for sequential recommendation tasks.
Our approach augments standard recommendation models with two output layers: one for self-supervised learning and the other for RL.
Based on such an approach, we propose two frameworks namely Self-Supervised Q-learning(SQN) and Self-Supervised Actor-Critic(SAC)
arXiv Detail & Related papers (2020-06-10T11:18:57Z) - Sequential Recommendation with Self-Attentive Multi-Adversarial Network [101.25533520688654]
We present a Multi-Factor Generative Adversarial Network (MFGAN) for explicitly modeling the effect of context information on sequential recommendation.
Our framework is flexible to incorporate multiple kinds of factor information, and is able to trace how each factor contributes to the recommendation decision over time.
arXiv Detail & Related papers (2020-05-21T12:28:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.